Related papers: Effective Token Graph Modeling using a Novel Label…

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their…

Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e,g,, target extraction or targeted polarity classification. We argue that…

Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks: (1) The internal…

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels…

Labeling datasets is a noteworthy challenge in machine learning, both in terms of cost and time. This research, however, leverages an efficient answer. By exploring label propagation in semi-supervised learning, we can significantly reduce…

By utilizing label distribution learning, a probability distribution is assigned for a facial image to express a compound emotion, which effectively improves the problem of label uncertainties and noises occurred in one-hot labels. In…

Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on…

Deep neural networks based on layer-stacking architectures have historically suffered from poor inherent interpretability. Meanwhile, symbolic probabilistic models function with clear interpretability, but how to combine them with neural…

We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis…

Multi-label sentiment classification plays a vital role in natural language processing by detecting multiple emotions within a single text. However, existing datasets like GoEmotions often suffer from severe class imbalance, which hampers…

Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on…

Structured sentiment analysis (SSA) aims to automatically extract people's opinions from a text in natural language and adequately represent that information in a graph structure. One of the most accurate methods for performing SSA was…

The classic supervised classification algorithms are efficient, but time-consuming, complicated and not interpretable, which makes it difficult to analyze their results that limits the possibility to improve them based on real observations.…

Multi-label text classification (MLTC) is an attractive and challenging task in natural language processing (NLP). Compared with single-label text classification, MLTC has a wider range of applications in practice. In this paper, we propose…

Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic description. A common ontology provides a way to represent the…

Graph Neural Networks (GNNs) have achieved great success among various domains. Nevertheless, most GNN methods are sensitive to the quality of graph structures. To tackle this problem, some studies exploit different graph structure learning…

Recently, prompt-based learning has gained popularity across many natural language processing (NLP) tasks by reformulating them into a cloze-style format to better align pre-trained language models (PLMs) with downstream tasks. However,…

While pre-trained language models excel at semantic understanding, they often struggle to capture nuanced affective information critical for affective recognition tasks. To address these limitations, we propose a novel framework for…

Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog…

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…